What are the hardware requirements for Zephyr 7B Gemma V0.1?

Zephyr 7B Gemma V0.1 requires approximately 17.1 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Zephyr 7B Gemma V0.1 and how large is it?

Zephyr 7B Gemma V0.1 is developed by HuggingFaceH4, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Zephyr 7B Gemma V0.1 perform on standard benchmarks?

Zephyr 7B Gemma V0.1 has the following published scores: MMLU 58.98. Compare against reference models on this page or on the LLM Explorer leaderboards.

Zephyr 7B Gemma V0.1 by HuggingFaceH4 — VRAM 17.1GB, 8K context

Name: Zephyr 7B Gemma V0.1
Author: HuggingFaceH4

Zephyr 7B Gemma V0.1 is an open-source language model by HuggingFaceH4. Features: 7b LLM, VRAM: 17.1GB, Context: 8K, License: other, HF Score: 61.5, LLM Explorer Score: 0.19, Arc: 57.9, HellaSwag: 82.9, MMLU: 59, TruthfulQA: 52.5, WinoGrande: 72.5, GSM8K: 44.1.

Arxiv:2310.16944 Alignment-handbook Base model:finetune:huggingfac... Base model:huggingfaceh4/zephy... Conversational Dataset:argilla/dpo-mix-7k Dpo Endpoints compatible Gemma Generated from trainer Model-index Region:us Safetensors Sharded Tensorboard Tensorflow Trl

Model Card on HF 🤗: https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1

Zephyr 7B Gemma V0.1 Benchmarks

IFEval: 33.64 vs 88 (so35)^-61.8%

ARC: 57.94 vs 96.7 (so35)^-40.1%

HellaSwag: 82.91 vs 95.3 (gpt4)^-13%

MMLU: 58.98 vs 88.3 (so35)^-33.2%

TruthfulQA: 52.47 vs 59 (gpt4)^-11.1%

WinoGrande: 72.53 vs 87.5 (gpt4)^-17.1%

GSM8K: 44.05 vs 96.4 (so35)^-54.3%

MATH Lvl 5: 8.16

LLME Score: 0.1941

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Zephyr 7B Gemma V0.1 (HuggingFaceH4/zephyr-7b-gemma-v0.1)

🌟 Advertise your project 🚀

Zephyr 7B Gemma V0.1 Parameters and Internals

Model Type

text generation

Additional Notes

Model is likely to generate problematic outputs since it was not aligned for safety with RLHF.

Supported Languages

primarily_english (full proficiency)

Training Details

Data Sources:

argilla/dpo-mix-7k

Methodology:

Direct Preference Optimization (DPO), fine-tuned on synthetic datasets

Model Architecture:

GPT-like architecture, fine-tuned variant

LLM Name	Zephyr 7B Gemma V0.1
Repository 🤗	https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1
Base Model(s)	HuggingFaceH4/zephyr-7b-gemma-sft-v0.1 HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
Model Size	7b
Required VRAM	17.1 GB
Updated	2026-01-27
Maintainer	HuggingFaceH4
Model Type	gemma
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 2.1 GB: 4-of-4 0.0 GB
Model Architecture	GemmaForCausalLM
License	other
Context Length	8192
Model Max Length	8192
Transformers Version	4.39.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Vocabulary Size	256000
Torch Data Type	bfloat16

Quantized Models of the Zephyr 7B Gemma V0.1

Model	Likes	Downloads	VRAM
Zephyr 7B Gemma V0.1 GGUF	6	208	3 GB

Best Alternatives to Zephyr 7B Gemma V0.1

Best Alternatives	Context / RAM	Downloads	Likes
Kaggle Math Model Gemma V1	12K / 17.1 GB	5	0
Gemma 1.1 7B It	8K / 17.1 GB	20065	275
Gemma 1.1 7B It	8K / 17.1 GB	28	4
Gemma 7B It	8K / 17.1 GB	1029	10
SeaLLM 7B V2.5	8K / 17.1 GB	12410	50
Zephyr 7B Gemma DPO Avg	8K / 17.1 GB	15	0
Zephyr 7B Gemma Rpo Avg	8K / 17.1 GB	7	0
... Codegemma 2 7B It Alpaca V1.3	8K / 17.1 GB	9	1
... 7B Finetuned Sft Navarasa 2.0	8K / 34 GB	314	23
Codegemma 7B It	8K / 17.1 GB	3605	251

Note: green Score (e.g. "73.2") means that the model is better than HuggingFaceH4/zephyr-7b-gemma-v0.1.

Rank the Zephyr 7B Gemma V0.1 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 53254 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Zephyr 7B Gemma V0.1 by HuggingFaceH4